Navigation registration method in brain neurosurgery department based on thermodynamic diagram and facial key points

Abstract

The invention discloses a navigation registration method in the brain neurosurgery department based on a thermodynamic diagram and facial key points, and belongs to the technical field of digital medical treatment. According to the method, an n-layer piling sand glass nerve network for extracting the key points based on the thermodynamic diagram is trained by utilizing human face key point data; then a CT three-dimensional image or MRI three-dimensional image of the head of the patient is acquired, and a facial three-dimensional grid key point cloud corresponding to the image is acquired and serves as a target point cloud; a binocular camera is utilized for capturing facial images of the patient in real time in an operation, and a binocular facial key point cloud of the patient is obtainedand serves as a source point cloud; finally, a singular value decomposition method is utilized for registration for the target point cloud and the source point cloud. The method is convenient to implement, low in cost, accurate in registration result and saves time, and additional wounds cannot be caused to the patient.

Description

technical field [0001] The invention relates to the field of digital medical technology, in particular to a brain neurosurgery navigation and registration method based on a heat map and facial key points. Background technique [0002] In modern neurosurgery, doctors usually need to collect medical images of the patient's head before the operation and analyze the lesion of the patient for preoperative surgical design. Medical images are registered, and the transformation matrix between the intraoperative scene coordinate space and the preoperative image coordinate space is obtained by using the registration results, so as to provide real-time guidance during the operation according to the preoperative design results, and real-time display of intraoperative surgical instruments in the preoperative medical position in the image. Among them, registration is a crucial part of neurosurgery navigation. [0003] Traditional neurosurgery navigation devices can be classified into in...

AI Technical Summary

Problems solved by technology

This method will introduce additional pain to the patient due to the bulky equipment. In addition, the method is not flexible and the accuracy is low.

The frameless mechanical navigation system developed later uses robotic arms and computer technology to achieve the purpose of positioning and tracking, but the system equipment is bulky and not easy to install

Ultrasonic positioning and navigation system uses the principle of ultrasonic ranging to calculate the spatial position of surgical instruments, but this method is not accurate, expensive and easily affected by the environment

The electromagnetic positioning and navigation system is based on multiple electromagnetic coils and uses electromagnetic induction to establish a three-dimensional space coordinate system by generating a three-dimensional low-frequency magnetic field for positioning. However, interfering electromagnetic waves in the surgical environment can easily affect positioning.

The infrared positioning and navigation system collects the active light source signal or the reflected light source signal, and determines the determination of the tracking object through calculation, but once the positioning light is blocked, it is easy to cause the loss of qualitative information

In addition, the prices of the above-mentioned various equipment are generally around one million yuan, and it is difficult to popularize them in ordinary local hospitals.

Collyer et al. proposed a novel registration and navigation method. This method obtains preoperative images by implanting metal markers in the patient's head, and then performing CT (Computed Tomography) scanning or MRI (Magnetic Resonance Imaging). Registration is achieved by capturing the markers during the operation to establish a mapping relationship. However, this method will cause the patient to suffer additional pain when the markers are implanted.

[0004] In the field of registration, although some methods based on patient surface features or additional markers have been proposed, such as using the iterative closest point method to register the source point cloud generated from the preoperative CT image with the intraoperative facial point cloud, these methods A better initial value is often required, otherwise it is easy to fall into a local optimal solution during the solution process, resulting in very large registration errors, and the accuracy is difficult to meet clinical requirements

Images